Abstract: We propose a generative adversarial network with multiple discriminators, which collaborate to represent a real dataset more effectively. This approach facilitates learning a generator consistent with the underlying data distribution based on real images and thus mitigates the chronic mode collapse problem. From the inspiration of multiple choice learning, we guide each discriminator to have expertise in the subset of the entire data and allow the generator to find reasonable correspondences between the latent and real data spaces automatically without the extra supervision for training examples. Despite the use of multiple discriminators, the backbone networks are shared across the discriminators and the increase of training cost is marginal. We demonstrate the effectiveness of our algorithm using multiple evaluation metrics in the standard datasets for diverse tasks.
Supplementary Material: zip